Anomaly Detection of Disconnects Using SSTDR and Variational Autoencoders

This article utilizes variational autoencoder (VAE) and spread spectrum time domain reflectometry (SSTDR) to detect, isolate, and characterize anomalous data (or faults) in a photovoltaic (PV) array. The goal is to learn the distribution of non-faulty input signals, inspect the reconstruction error of test signals, flag anomalies, and then locate or characterize the anomalous data using a predicted baseline rather than a fixed baseline that might be too rigid. The use of VAE handles imbalanced data better than other methods used for classification of PV faults because of its unsupervised nature. We consider only disconnects in this work, and our results show an overall accuracy of 96% for detecting true negatives (non-faulty data), a 99% true positive rate of detecting anomalies, 0.997 area under the ROC curve, 0.99 area under the precision-recall curve, and a maximum percentage absolute relative error of 0.40% in locating the faults on a 5-panel setup with a 59.13 m leader cable.

Automated summary

This article uses variational autoencoder (VAE) and spread spectrum time domain reflectometry (SSTDR) to detect and locate anomalous data in photovoltaic (PV) arrays. By learning the distribution of non-faulty input signals and using predicted baselines, it handles imbalanced data effectively. The results demonstrate high accuracy and detection rates in disconnect detection.